用轻量模块实现精准运动规划，速度提升15倍且通用性强。
BridgeFlow: Fast and Robust SE(2)-Equivariant Motion Planning with Flow Matching
- 通过任务中心化模块实现严格空间等变性，无需复杂网络。
- 结合布朗桥先验与最优传输，推理速度提升15倍，有效轨迹率翻倍。
- 适合需要实时性与强泛化能力的机器人路径规划场景。
在机器人运动规划中，对刚体变换的等变性对鲁棒的空间泛化至关重要。然而，现有学习方法面临两难：要么缺乏内在等变性，将变换后任务视为新场景；要么依赖计算开销大的专用架构，阻碍实时推理。为此，我们提出BridgeFlow，一种快速且严格满足SE(2)等变性的生成式运动规划框架。不同于依赖重型等变网络，BridgeFlow通过轻量级任务中心化模块实现精确空间等变性，支持使用标准架构进行泛化。为加速推理，采用布朗桥信息先验与上下文感知小批量最优传输，构建低运输成本的平滑向量场，稳定训练过程。环境感知通过无分类器引导显式嵌入。在密集2D环境及7自由度Franka机械臂上的评估表明，BridgeFlow相较最先进扩散基线实现最高15倍推理加速、2倍有效轨迹率提升，同时对完全未见环境和任意空间变换保持强泛化能力。
原文摘要 · Abstract (English)
In robotic motion planning, equivariance to rigid body transformations is crucial for robust spatial generalization. However, current learning-based planners face a critical dilemma: they either lack inherent equivariance, treating transformed tasks as novel scenarios, or enforce it via computationally expensive specialized architectures that bottleneck real-time inference. To break this trade-off, we propose BridgeFlow, a fast and strictly SE(2)-equivariant generative motion planning framework. Rather than relying on heavy equivariant networks, BridgeFlow achieves exact spatial equivariance via a lightweight task-centric canonicalization module, enabling generalization using standard architectures. To further accelerate inference, we pair a Brownian bridge informative prior with context-aware mini-batch optimal transport. This constructs a straightened vector field that minimizes transport costs and stabilizes training. Furthermore, environmental awareness is explicitly embedded via Classifier-Free Guidance. Evaluations in dense 2D environments and on a 7-DoF Franka manipulator demonstrate that BridgeFlow achieves up to a 15x inference speedup and a 2x higher valid trajectory rate over state-of-the-art diffusion baselines, alongside robust generalization to entirely unseen environments and arbitrary spatial transformations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。